Wonder

Wonder is an enhancement designed for professionals who want a simple, reliable way to improve small or medium sized low-resolution images that have compression artifacts, without stacking multiple tools. Traditional workflows can over-process or introduce artifacts when several enhancements are combined. Wonder is an automatic image repair tool to deliver very high-quality, artifact-free results on medium and low-quality images. It’s able to generate clean outputs, especially with fine details that other models may struggle with.

Important: This model is for small or medium low-resolution images that are soft, noisy, compressed, for example, and where you want clean, realistic detail without artifacts.

It is not for images shot on modern cameras, or RAW files. Using the model on images that are not meant for the model will have issues, inconsistent behavior and results, and editing images that fall outside its intended use is not supported. For RAW images or images from modern cameras, you can use other enhancements meant for these files such as RAW Denoise, Denoise, Sharpen, Recover Faces, Upscale, etc.

The maximum output for this Wonder generative model is 128MP (megapixels). If you have issues rendering your image, test a smaller starting file or contact us at Support and we can troubleshoot. Make sure to send to Support the file you are working with for us to see what model is meant for the image.

How to Access Wonder from the Filter menu:
Note: if Auto-Pilot is on, this "Select a Filter" button will be named "Choose something else"

Results examples on this heavily compressed file:

Wonder v2 release

The Wonder v2 model was released in Topaz Photo v1.2.0. It is our most impressive all-in-one realism model so far. It’s built to handle extremely difficult images and produce outputs that look clean, natural, and professional. Wonder 2 is a great choice when realism is the top priority and you want a safe model for professional work.

If Wonder v1 felt too stylized for certain images, Wonder v2 is designed to feel more restrained and natural.

Key things to know

Wonder v2 will work best when Cloud Processing: Because of the computational resources required to run this model, Wonder v2 will give best results on the Cloud.
Single-step model with no preview controls
Best results when upscaling 4x
Not recommended for low-light phone images with heavy noise

Wonder v1 and v2 models are for low-resolution or challenging source images that need strong cleanup and enhancement and that have compression artifacts to fix. It is not to be used for high-resolution images, or for imags shot on modern cameras, and is not for images that are already sharp. images

Wonder will not work as a Preset

Local Rendering

Wonder v1
Local rendering is available if you:

Have a Topaz Pro license or Founder status
Use a machine that meets the minimum system requirements

When these conditions are met, Wonder v1 can run locally on your machine.

Wonder v2
Introduced in Topaz Photo v1.3.1, Wonder v2 Local is a smaller version of the Wonder v2 cloud model designed for local processing.

Local Wonder v2 requires:

Windows: NVIDIA or AMD Graphic card with 8GB VRAM or more
Mac: Apple Silicon (M-series) machines

Not supported on:

Intel Macs
Windows ARM / Snapdragon systems

For faster processing and the highest quality results, we recommend using Cloud Processing, which runs the full Wonder v2 model.

Cloud Rendering

You can run Wonder v1 or Wonder v2 using Cloud Processing.

Uses the full model for Wonder v2 vs local
Provides faster processing
Produces more detailed results for Wonder v2 vs Local

Contact Support

If you have issues using the model, contact us at Support and we can troubleshoot. When you write in, make sure to provide:

The image you are trying to upscale. Make sure it's a low-resolution or compressed file, which will be a case for the Wonder model.
Details on the issue: Local or cloud processing? Details on the behavior and screenshots of the error you get, if any.
Your app's logs: Help menu > Open Logs folder > Attach all the logs you see in the email to Support.

Upscale & Resize

Generative Models